Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    instances of the word "undermine" and its variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    κÎŃ
    -0.17
    ToProps
    -0.17
    odi
    -0.15
    asso
    -0.15
    ê·¹
    -0.15
    ALLE
    -0.14
    dek
    -0.14
    ANNEL
    -0.14
    Assertions
    -0.14
    utoff
    -0.14
    POSITIVE LOGITS
    lessly
    0.15
     efforts
    0.15
    ninger
    0.14
    æİī
    0.14
    pecies
    0.14
    597
    0.14
    398
    0.13
    ingly
    0.13
     effort
    0.13
     inn
    0.13
    Act Density 0.013%

    No Known Activations